Open Access. Powered by Scholars. Published by Universities.®
- Institution
-
- China Simulation Federation (3924)
- Singapore Management University (1936)
- Old Dominion University (660)
- San Jose State University (277)
- MMU Press (252)
-
- MBZUAI (233)
- City University of New York (CUNY) (185)
- Technological University Dublin (157)
- Air Force Institute of Technology (138)
- Chapman University (127)
- Chinese Academy of Sciences (117)
- California Polytechnic State University, San Luis Obispo (116)
- University of Arkansas, Fayetteville (105)
- Edith Cowan University (101)
- Lindenwood University (97)
- Embry-Riddle Aeronautical University (94)
- University of South Florida (80)
- University of Nebraska - Lincoln (79)
- University of Kentucky (76)
- University of Malaya (72)
- University of Nevada, Las Vegas (64)
- Clemson University (63)
- Dartmouth College (62)
- University of Denver (59)
- University of Michigan Law School (59)
- Utah State University (57)
- Thomas Jefferson University (55)
- University of Texas at El Paso (55)
- New Jersey Institute of Technology (54)
- University of Central Florida (51)
- Keyword
-
- Artificial intelligence (789)
- Machine learning (695)
- Deep learning (447)
- Machine Learning (422)
- Artificial Intelligence (384)
-
- AI (242)
- Deep Learning (232)
- Computer vision (162)
- Simulation (159)
- Generative AI (142)
- Reinforcement learning (141)
- Neural networks (130)
- Large language models (111)
- Natural language processing (108)
- Natural Language Processing (104)
- Robotics (97)
- ChatGPT (91)
- Path planning (89)
- Computer Vision (86)
- Optimization (85)
- Large Language Models (83)
- Classification (76)
- Neural network (69)
- Cybersecurity (66)
- Virtual reality (65)
- Neural Networks (64)
- Reinforcement Learning (64)
- Computer Science (60)
- Deep reinforcement learning (60)
- Genetic algorithm (58)
- Publication Year
- Publication
-
- Journal of System Simulation (3924)
- Research Collection School Of Computing and Information Systems (1697)
- Journal of Informatics and Web Engineering (252)
- Master's Projects (248)
- Theses and Dissertations (183)
-
- Computer Science Faculty Publications (128)
- Bulletin of Chinese Academy of Sciences (Chinese Version) (117)
- Faculty Scholarship (109)
- Publications and Research (100)
- Computer Vision Faculty Publications (98)
- Master's Theses (96)
- Conference papers (92)
- Electrical & Computer Engineering Faculty Publications (91)
- Machine Learning Faculty Publications (86)
- Electronic Theses and Dissertations (85)
- Faculty Publications (79)
- Research outputs 2022 to 2026 (73)
- Dissertations (71)
- USF Tampa Graduate Theses and Dissertations (67)
- Dissertations and Theses Collection (Open Access) (60)
- Articles (56)
- Dissertations, Theses, and Capstone Projects (53)
- Open Access Theses & Dissertations (51)
- Theses and Dissertations--Computer Science (48)
- Natural Language Processing Faculty Publications (46)
- Teaching and Generative AI: Pedagogical Possibilities and Productive Tensions (46)
- Graduate Theses and Dissertations (45)
- Student Works (2000-2009) (42)
- Electrical & Computer Engineering Theses & Dissertations (41)
- Graduate Theses, Dissertations, and Problem Reports (ETD) (40)
- Publication Type
- File Type
Articles 2611 - 2640 of 11645
Full-Text Articles in Entire DC Network
Flexible Hybrid Self-Powered Piezo-Triboelectric Nanogenerator Based On Bto-Pvdf/Pdms Nanocomposites For Human Machine Interaction, Wentao Dong, Mengyun Li, Chang Chen, Kun Xie, Jinhua Hong, Lin Yang
Flexible Hybrid Self-Powered Piezo-Triboelectric Nanogenerator Based On Bto-Pvdf/Pdms Nanocomposites For Human Machine Interaction, Wentao Dong, Mengyun Li, Chang Chen, Kun Xie, Jinhua Hong, Lin Yang
Civil & Environmental Engineering Faculty Publications
As flexible and wearable electronics play more and more important role in smart watches, smart glass and virtual reality, and the power supply to the wearable electronics have been revealed more attentions for long-term usage and continuous healthy monitoring. To overcome the challenge, flexible self-powered BTO-PVDF/PDMS piezoelectric-triboelectric electric hybrid generators (BPP-HNG) are developed to human gesture monitoring and human machine interaction (HMI) application without external power supply. BPP-HNG based on BTO-PVDF and PDMS films are prepared by sol-gel and spin-coating method. When the BTO content is 20 wt.%, BPP-HNG exhibits better electrical performance with an output voltage of 20.51 V. …
Organic Geochemical Evidence For Life In Archean Rocks Identified By Pyrolysis-Gc-Ms And Supervised Machine Learning, Michael L. Wong, Anirudh Prabhu, Conel O'D. Alexander, H. James Cleaves Ii, George D. Cody, Grethe Hystad, Marko Bermanec, Wouter Bleeker, C. Kevin Boyce, Andrea Corpolongo, Andrew D. Czaja, Souvik Das, Robert R. Gaines, Daniel D. Gregory, John A. Jaszczak, Emmanuelle J. Javaux, Jaganmoy Jodder, Andrew H. Knoll, Martin Van Kranendonk, Katie M. Maloney, Nora Noffke, Robert Rainbird, Emersyn Slaughter, Eva E. Stüeken, Roger E. Summons, Frances Westall, Jasmina Wiemann, Shuhai Xiao, Robert M. Hazen
Organic Geochemical Evidence For Life In Archean Rocks Identified By Pyrolysis-Gc-Ms And Supervised Machine Learning, Michael L. Wong, Anirudh Prabhu, Conel O'D. Alexander, H. James Cleaves Ii, George D. Cody, Grethe Hystad, Marko Bermanec, Wouter Bleeker, C. Kevin Boyce, Andrea Corpolongo, Andrew D. Czaja, Souvik Das, Robert R. Gaines, Daniel D. Gregory, John A. Jaszczak, Emmanuelle J. Javaux, Jaganmoy Jodder, Andrew H. Knoll, Martin Van Kranendonk, Katie M. Maloney, Nora Noffke, Robert Rainbird, Emersyn Slaughter, Eva E. Stüeken, Roger E. Summons, Frances Westall, Jasmina Wiemann, Shuhai Xiao, Robert M. Hazen
OES Faculty Publications
Throughout Earth’s history, organic molecules from both abiogenic and biogenic sources have been buried in sedimentary rocks. Most of these organic molecules have been significantly altered by geologic processes through deep time. Nonetheless, the nature and distribution of those ancient fragmentary organic remains have the potential to reveal diagnostic biomolecular information after billions of years of burial. Here, we analyzed 406 fossil, modern biological, meteoritic, and synthetic samples using pyrolysis gas chromatography and mass spectrometry. We explored these analytical data via supervised machine-learning methods to discriminate samples of biogenic vs. abiogenic origin, plant vs. animal phylogenetic affinity, and photosynthetic vs. …
Towards Human Explainable Digital Forensics: Generating Human Interpretable Evidence For Semantic Understanding In Manipulated Images And Text, Yuwei Chen
Electronic Theses & Dissertations (2024 - present)
Detecting and characterizing manipulations in digital media continues to pose a significant challenge within the field of digital forensics. Despite notable advancements, the discipline often remains in a reactive stance against emerging threats. Current state-of-the-art methods, typically evaluated within academic settings, fails to mirror the complexities of real-world disinformation scenarios. These methods generally prioritize high performance based on quantitative metrics, yet they demonstrate a considerable dependency on training data and lack adaptability to new novel attack signatures. With the rapid evolution of attack methodologies, the dependency on highly accurate models that do not generalize or adapt well to unseen threats …
Design And Analysis Of Facial Recognition Algorithms For Home Monitoring, Nathaniel F. Bernich
Design And Analysis Of Facial Recognition Algorithms For Home Monitoring, Nathaniel F. Bernich
Honors Theses and Capstones
Facial recognition "in the wild" has posed a challenge in the field of computer vision. Though facial recognition algorithms are generally proficient at recognizing faces up close, subjects at awkward angles and greater distances from the camera make monitoring areas with this software a practical challenge. At UNH's Cognitive Assistive Robotics Lab (CARL), overcoming the weak areas of face recognition is essential to the task of home monitoring. The CARL research team is implementing a suite of robotics and computer vision technologies to monitor patients with Alzheimer's dementia in their homes. This necessitates a reliable and effective facial recognition pipeline …
Panoscu: A Simulation-Based Dataset For Panoramic Indoor Scene Understanding, Mariia Khan, Yue Qiu, Yuren Cong, Jumana Abu-Khalaf, David Suter, Bodo Rosenhahn
Panoscu: A Simulation-Based Dataset For Panoramic Indoor Scene Understanding, Mariia Khan, Yue Qiu, Yuren Cong, Jumana Abu-Khalaf, David Suter, Bodo Rosenhahn
Research outputs 2022 to 2026
Panoramic images offer a comprehensive spatial view that is crucial for indoor robotics tasks such as visual room rearrangement, where an agent must restore objects to their original positions or states. Unlike existing 2D scene change understanding datasets, which rely on single-view images, panoramic views capture richer spatial context, object relationships, and occlusions—making them better suited for embodied artificial intelligence (AI) applications. To address this, we introduce Panoramic Scene Change Understanding (PanoSCU), a dataset specifically designed to enhance the visual object rearrangement task. Our dataset comprises 5,300 panoramas generated in an embodied simulator, encompassing 48 common indoor object classes. PanoSCU …
A Case Study Using The Transparency Framework And Artificial Intelligence To Promote Effective Writing And Student Success In A Writing-Intensive Course, Elizabeth A. Brown, Maria Kronenburg, Ashlee Steeley, Diana Tagbor
A Case Study Using The Transparency Framework And Artificial Intelligence To Promote Effective Writing And Student Success In A Writing-Intensive Course, Elizabeth A. Brown, Maria Kronenburg, Ashlee Steeley, Diana Tagbor
Health Behavior, Policy & Management Faculty Publications
Program evaluation data suggest that undergraduate students struggle with writing in a clear and concise manner and appropriately citing. Faculty implemented the plan-do study-act cycle to pilot the Transparency in Learning and Teaching (TILT) project framework and to explore the use of artificial intelligence (AI) and discuss approaches to using AI, along with the TILT framework, in a writing-intensive course to identify the pros and cons of using ChatGPT in an online classroom. The TILT framework reinforces adult learning by helping students clearly understand the assignment's purpose and establish a clear relationship between assignment and students' professional lives. Faculty encouraged …
A Qualitative Analysis Of College Students' Interest In Mhealth Solutions, Leslie Hoglund, Craig M. Becker, Cara Tonn
A Qualitative Analysis Of College Students' Interest In Mhealth Solutions, Leslie Hoglund, Craig M. Becker, Cara Tonn
Health Behavior, Policy & Management Faculty Publications
This study explores college students' perceptions of an AI-driven mHealth application designed to promote well-being. With rising mental health challenges in academic settings, students increasingly seek digital tools that provide holistic support for physical, mental, and financial health. Through focus groups, this qualitative study examines students' preferences for personalized health tracking, educational content, and flexible reminders within a private, supportive community. Key findings emphasize students' desire for a balanced, all-in-one app that integrates health and wellness tools without overwhelming them with notifications. Students also highlighted the importance of social media integration for outreach, though concerns were raised about potential stress …
Examining Teaching Competencies And Challenges While Integrating Artificial Intelligence In Higher Education, Xinyue Ren, Min Lun Wu
Examining Teaching Competencies And Challenges While Integrating Artificial Intelligence In Higher Education, Xinyue Ren, Min Lun Wu
STEMPS Faculty Publications
The rapid development of artificial intelligence (AI) technologies has demonstrated their affordances and limitations in revolutionizing pedagogical strategies in higher education. Given the lack of guidelines, policies, and resources to assist instructors in efficiently and ethically integrating AI into teaching and learning practices, this systematic review aimed to investigate AI integration competencies and challenges in higher education from the intelligent Technological Pedagogical Content Knowledge (TPACK) perspective. We first applied the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) to identify 23 studies published between 2019 and 2023 that met the inclusion and exclusion criteria. After conducting open coding and …
Nexus: Network Exploration For Exploiting Unsafe Sequences In Multi-Turn Llm Jailbreaks, Javad Rafiei Asl, Sidhant Narula, Mohammad Ghasemigol, Eduardo Blanco, Daniel Takabi
Nexus: Network Exploration For Exploiting Unsafe Sequences In Multi-Turn Llm Jailbreaks, Javad Rafiei Asl, Sidhant Narula, Mohammad Ghasemigol, Eduardo Blanco, Daniel Takabi
School of Cybersecurity Faculty Publications
Large Language Models (LLMs) have revolutionized natural language processing, yet remain vulnerable to jailbreak attacks—particularly multi-turn jailbreaks that distribute malicious intent across benign exchanges, thereby bypassing alignment mechanisms. Existing approaches often suffer from limited exploration of the adversarial space, rely on hand-crafted heuristics, or lack systematic query refinement. We propose NEXUS (Network Exploration for eXploiting Unsafe Sequences), a modular framework for constructing, refining, and executing optimized multi-turn attacks. NEXUS comprises: (1) ThoughtNet, which hierarchically expands a harmful intent into a structured semantic network of topics, entities, and query chains; (2) a feedback-driven Simulator that iteratively refines and prunes these chains …
Problem-Centered Post-Secondary Computer Science Education: A Study Of The Private Artificial Intelligence Curriculum, Golnoush Haddadian, Prajwal Panzade, Daniel Takabi, Min Kyu Kim
Problem-Centered Post-Secondary Computer Science Education: A Study Of The Private Artificial Intelligence Curriculum, Golnoush Haddadian, Prajwal Panzade, Daniel Takabi, Min Kyu Kim
School of Cybersecurity Faculty Publications
In response to the demand for Artificial Intelligence (AI) experts, this study introduced a curriculum development initiative. The aim was to design and implement a Private AI curriculum to understand the computer science (CS) students’ evaluations of the curricular activities and their levels of interest and motivation. Twenty-five students, a mix of undergraduates and graduates, were recruited and a scaled-down version of the curriculum was implemented. A parallel mixed-methods approach was employed. The results reinforced the significance of problem-centered curricula in CS context. Students rated the curricular activities highly and demonstrated strong motivation; however, graduates expressed more favorable view of …
Privacy-Preserved And Incentivized Knowledge Sharing For Reinforced-Learning Based Iot Platform Security, Weichao Wang, Md Morshed Alam, Yu Wang
Privacy-Preserved And Incentivized Knowledge Sharing For Reinforced-Learning Based Iot Platform Security, Weichao Wang, Md Morshed Alam, Yu Wang
School of Cybersecurity Faculty Publications
With the fast development and deep penetration of IoT devices and smart environments, using localized machine learning models to detect malicious activities has also been developed and deployed. However, these isolated learning models and results cannot be effectively federated together because of privacy concerns and lack of incentivization. This paper proposed several mechanisms to solve the problem. A verification method was designed for phased learning results to protect user privacy and prevent individual parties from manipulating the verification selection. The paper also presented an incentive method based on delay of distribution of the latest federated learning results. Extensive simulations were …
Security Enhancement In Uav Swarms: A Case Study Using Federated Learning And Shap Analysis, Sushmitha Halli Sudhakara, Lida Haghnegahdar
Security Enhancement In Uav Swarms: A Case Study Using Federated Learning And Shap Analysis, Sushmitha Halli Sudhakara, Lida Haghnegahdar
School of Cybersecurity Faculty Publications
As cyber-physical systems (CPSs) increasingly integrate physical and digital realms, securing critical infrastructure, such as the Port of Virginia, becomes paramount. Among CPSs, Unmanned Aerial Vehicles (UAVs) are vital for monitoring, communication, and supporting the command and control through remote reconnaissance and surveillance missions. These UAV applications often require coordination, planning, and runtime reconfiguration, traditionally managed by human decision-makers. However, this approach has limitations, as extensively documented in the literature. Artificial Intelligence (AI) has emerged as a pivotal tool to address these limitations, enhancing risk mitigation and informed decision-making. This research proposes a machine learning (ML) based security mechanism, leveraging …
Deepsecure: A Novel Deep Learning Model For Effective Detection Of Attacks On Big Data In Internet Of Urban Things, Laiba Sabir, Nadeem Javaid, Mariam Akbar, Nabil Alrajeh, Safdar Hussain Bouk, Abdulaziz Aldegheishem
Deepsecure: A Novel Deep Learning Model For Effective Detection Of Attacks On Big Data In Internet Of Urban Things, Laiba Sabir, Nadeem Javaid, Mariam Akbar, Nabil Alrajeh, Safdar Hussain Bouk, Abdulaziz Aldegheishem
School of Cybersecurity Faculty Publications
The Internet of Urban Things (IoUTs) regularly generates large amounts of data, making it a focus of cyberthreats such as denial-of-service attacks and malware bot networks. Traditional intrusion detection systems struggle to detect intricate attack patterns, handle class imbalance, capture temporal dependencies, and exhibit transparency. To address these limitations, we introduce a novel deep machine learning model, DeepSecure, a hybrid model that combines Deep Belief Networks (DBN) for hierarchical feature extraction and Deep Neural Networks for attack classification. DBN is used for feature selection through unsupervised learning to extract hierarchical representations in the IoUTs network data. We assess the random …
Security Enhancement In Aav Swarms: A Case Study Using Federated Learning And Shap Analysis, Sushmitha Halli Sudhakara, Lida Haghnegahdar
Security Enhancement In Aav Swarms: A Case Study Using Federated Learning And Shap Analysis, Sushmitha Halli Sudhakara, Lida Haghnegahdar
School of Cybersecurity Faculty Publications
As cyber-physical systems (CPSs) increasingly integrate physical and digital realms, securing critical infrastructure, such as the Port of Virginia, becomes paramount. Among CPSs, Autonomous Aerial Vehicles (AAVs) are vital for monitoring, communication, and supporting the command and control through remote reconnaissance and surveillance missions. These AAV applications often require coordination, planning, and runtime reconfiguration, traditionally managed by human decision-makers. However, this approach has limitations, as extensively documented in the literature. Artificial Intelligence (AI) has emerged as a pivotal tool to address these limitations, enhancing risk mitigation and informed decision-making. This research proposes a machine learning (ML) based security mechanism, leveraging …
Tl-Convlstm: A Transfer-Learning-Based Convolutional Lstm To Identify And Forecast Traffic In The Nextg Environments, Bikash Chandra Singh, Peter Foytik, Rafael Diaz, Sachin Shetty
Tl-Convlstm: A Transfer-Learning-Based Convolutional Lstm To Identify And Forecast Traffic In The Nextg Environments, Bikash Chandra Singh, Peter Foytik, Rafael Diaz, Sachin Shetty
School of Cybersecurity Faculty Publications
Forecasting and categorizing cellular traffic flows and their types are essential functions in intelligent network systems to ensure efficient network optimization. The ever-evolving nature of 5G networks results in fluctuations in traffic patterns over time, leading to a phenomenon known as model drift. Consequently, accurately predicting and identifying cellular traffic patterns becomes a complex task. To tackle this challenge, this article introduces an innovative approach called TL-ConvLSTM, which combines transfer learning with convolutional long short-term memory (ConvLSTM) to effectively combat model drift and provide precise forecasting and recognition of cellular traffic within the network. To accomplish this, we initiate the …
Transforming Urban Dynamics: Harnessing Large Language Models For Smarter Mobility, Hao Xue, Ming Jin, Shirui Pan, Flora Salim, Guansong Pang
Transforming Urban Dynamics: Harnessing Large Language Models For Smarter Mobility, Hao Xue, Ming Jin, Shirui Pan, Flora Salim, Guansong Pang
Research Collection School Of Computing and Information Systems
Artificial intelligence (AI) has the potential to analyze mobility data and make mobility systems smarter by leveraging diverse data sources such as geospatial data, transportation logs, and real-time sensor data to optimize traffic flow, enhance public transportation systems, and support the development of autonomous vehicles. With the newly emerged generative AI paradigm, exemplified by large language models (LLMs), there is great potential to transform the current AI applications in mobility, transportation, and urban domains. This article provides an overview of recent efforts and aims to shed light on the challenges and future opportunities to facilitate the adaptation of LLMs for …
Prompt-Based Learning For Few-Shot Class-Incremental Learning, Jicheng Yuan, Hang Chen, Songsong Tian, Wenfa Li, Lusi Li, Enhao Ning, Yugui Zhang
Prompt-Based Learning For Few-Shot Class-Incremental Learning, Jicheng Yuan, Hang Chen, Songsong Tian, Wenfa Li, Lusi Li, Enhao Ning, Yugui Zhang
Computer Science Faculty Publications
Few-Shot Class-Incremental Learning (FSCIL) aims to enable deep neural networks to incrementally learn new tasks from a limited number of labeled samples, while retaining knowledge of previously learned tasks, mimicking the way humans learn. In this paper, we introduce a novel approach called Prompt Learning for FSCIL (PL-FSCIL), which leverages the power of prompts alongside a pre-trained Vision Transformer (ViT) model to effectively tackle the challenges of FSCIL. Our approach explores the feasibility of directly applying visual prompts in FSCIL, using a simplified model architecture. PL-FSCIL integrates two key prompts: the Domain Prompt and the FSCIL Prompt. Both are tensors …
Sting: A Stealthy Backdoor Attack On Gnn-Based Malicious Domain Detection Via Dns Perturbations, Muhammad Anan, Mahmoud Nazzal, Abdallah Khreishah, Issa Khalil, Nhathai Phan, Ahmad Sawalmeh
Sting: A Stealthy Backdoor Attack On Gnn-Based Malicious Domain Detection Via Dns Perturbations, Muhammad Anan, Mahmoud Nazzal, Abdallah Khreishah, Issa Khalil, Nhathai Phan, Ahmad Sawalmeh
Computer Science Faculty Publications
Detecting malicious Internet domains is essential for safeguarding against various online threats. The current approach to detecting malicious domains (MDD) employs a graph neural network (GNN) method, which uses DNS logs to construct heterogeneous graphs for determining the maliciousness of unknown domains. Despite its success, this method is vulnerable to data poisoning attacks where an adversary can manipulate specific graph nodes to implant a backdoor into the model during training. To showcase the vulnerability, we propose a stealthy trigger injection attack on node features and graph structure in MDD, dubbed (STING). The attacker carefully manipulates selected features and edges of …
Normalizing Images In Various Weather And Lighting Conditions Using Colorpix2pix Generative Adversarial Network, Sanjida Tasnim, Ashif Mahmud Mostafa, Azmain Morshed, Namreen Shaiyaz, Shakib Mahmud Dipto, Saad Aloteibi, Mohammad Ali Moni, Md. Golam Rabiul Alam, Md. Ashraful Alam
Normalizing Images In Various Weather And Lighting Conditions Using Colorpix2pix Generative Adversarial Network, Sanjida Tasnim, Ashif Mahmud Mostafa, Azmain Morshed, Namreen Shaiyaz, Shakib Mahmud Dipto, Saad Aloteibi, Mohammad Ali Moni, Md. Golam Rabiul Alam, Md. Ashraful Alam
Computer Science Faculty Publications
Autonomous vehicles (AVs) are widely regarded as the future of transportation due to their tremendous benefits and user comfort. However, the AVs have been struggling with very crucial challenges, such as achieving reliable accuracy in object detection as well as faster computation required for quick decision-making. In recent years, perception systems in driverless cars have been significantly enhanced, mainly due to advances in deep-learning-based object detection systems. However, these perception systems are still heavily affected by environmental variables, such as changes in illumination, refractive interference, and adverse weather conditions, which may compromise their reliability and safety. This research proposes an …
Coldstartcpi: Induced-Fit Theory-Guided Dti Predictive Model With Improved Generalization Performance, Qichang Zhao, Haochen Zhao, Linyuan Gao, Kai Zheng, Yajie Li, Qiao Ling, Jing Tang, Yaohang Li, Jianxin Wang
Coldstartcpi: Induced-Fit Theory-Guided Dti Predictive Model With Improved Generalization Performance, Qichang Zhao, Haochen Zhao, Linyuan Gao, Kai Zheng, Yajie Li, Qiao Ling, Jing Tang, Yaohang Li, Jianxin Wang
Computer Science Faculty Publications
Predicting compound-protein interactions (CPIs) plays a crucial role in drug discovery. Traditional methods, based on the key-lock theory and rigid docking, often fail with novel compounds and proteins due to their inability to account for molecular flexibility and the high sparsity of CPI data. Here, we introduce ColdstartCPI, a framework inspired by induced-fit theory, which leverages unsupervised pre-training features and a Transformer module to learn both compound and protein characteristics. ColdstartCPI treats proteins and compounds as flexible molecules during inference, aligning with biological insights. It outperforms state-of-the-art sequence-based models, particularly for unseen compounds and proteins, and shows strong generalization capability …
Can Llms Beat Humans On Discerning Human-Written And Llm-Generated Science News, Dominik Soós, Meng Jiang, Jian Wu
Can Llms Beat Humans On Discerning Human-Written And Llm-Generated Science News, Dominik Soós, Meng Jiang, Jian Wu
Computer Science Faculty Publications
Science news is increasingly important in connecting scientists and the public by sharing discoveries and innovations. With the rise of large language models (LLMs), there is potential to automate science news creation, but concerns exist about the quality of LLM-generated news versus human-written news. This paper explores whether LLMs can outperform humans in distinguishing between human-written and LLM-generated news. Inspired by the Chain-of-Thought prompting method, we designed a simple yet effective variant called Guided Few-shot (GFS), which encodes the characteristics of news of two types with examples. Our experiments indicated that GFS with just a single example effectively boosted the …
From Philosophy To Nlu: Evolving Definitions With Research Hypotheses, Jian Wu, Sarah Rajtmajer
From Philosophy To Nlu: Evolving Definitions With Research Hypotheses, Jian Wu, Sarah Rajtmajer
Computer Science Faculty Publications
Over the past decades, alongside advancements in natural language processing, significant attention has been paid to training models to automatically extract, understand, test, and generate hypotheses in open and scientific domains. However, interpretations of the term hypothesis for various natural language understanding (NLU) tasks have migrated from traditional definitions in the natural, social, and formal sciences. Even within NLU, we observe differences defining hypotheses across literature. In this paper, we overview and delineate various definitions of hypothesis. Especially, we discern the nuances of definitions across recently published NLU tasks. We highlight the importance of well-structured and well-defined hypotheses, particularly as …
From Philosophy To Nlu: Evolving Definitions Of Research Hypotheses, Jian Wu, Sarah Rajtmajer
From Philosophy To Nlu: Evolving Definitions Of Research Hypotheses, Jian Wu, Sarah Rajtmajer
Computer Science Faculty Publications
Over the past decades, alongside advancements in natural language processing, significant attention has been paid to training models to automatically extract, understand, test, and generate hypotheses in open and scientific domains. However, interpretations of the term hypothesis for various natural language understanding (NLU) tasks have migrated from traditional definitions in the natural, social, and formal sciences. Even within NLU, we observe differences defining hypotheses across literature. In this paper, we overview and delineate various definitions of hypothesis. Especially, we discern the nuances of definitions across recently published NLU tasks. We highlight the importance of well-structured and well-defined hypotheses, particularly as …
Optiselect And Enshap: Integrating Machine Learning And Game Theory For Ischemic Stroke Prediction, Pritam Chakraborty, Anjan Bandyopadhyay, Sricheta Parul, Sujata Swain, Partha Sarathy Banerjee, Tapas Si, Hong Qin, Saurav Mallik
Optiselect And Enshap: Integrating Machine Learning And Game Theory For Ischemic Stroke Prediction, Pritam Chakraborty, Anjan Bandyopadhyay, Sricheta Parul, Sujata Swain, Partha Sarathy Banerjee, Tapas Si, Hong Qin, Saurav Mallik
Computer Science Faculty Publications
Stroke analysis using game theory and machine learning techniques. The study investigates the use of the Shapley value in predictive ischemic brain stroke analysis. Initially, preference algorithms identify the most important features in various machine learning models, including logistic regression, K-nearest neighbor, decision tree, support vector machine (linear kernel), support vector machine ( RBF kernel), neural networks, etc. For each sample, the top 3, 4, and 5 features are evaluated and selected to evaluate their performance. The Shapley value method was used to rank the models using their best four features based on their predictive capabilities. As a result, better-performing …
S²Il: Structurally Stable Incremental Learning, S. Balasubramanian, P. Yedu Krishna, Talasu Sai Sriram, M. Sai Subramaniam, Manepalli Pranav Phanindra Sai, Ravi Mukkamala
S²Il: Structurally Stable Incremental Learning, S. Balasubramanian, P. Yedu Krishna, Talasu Sai Sriram, M. Sai Subramaniam, Manepalli Pranav Phanindra Sai, Ravi Mukkamala
Computer Science Faculty Publications
Feature Distillation (FD) strategies are proven to be effective in mitigating Catastrophic Forgetting (CF) seen in Class Incremental Learning (CIL). However, current FD approaches enforce strict alignment of feature magnitudes and directions across incremental steps, limiting the model’s ability to adapt to new knowledge. In this paper, we propose Structurally Stable Incremental Learning (S²IL), a FD method for CIL that mitigates forgetting by focusing on preserving the overall spatial patterns of features which promote flexible (plasticity) yet stable representations that preserve old knowledge (stability). We also demonstrate that our proposed method S²IL achieves strong incremental accuracy and outperforms other FD …
Neural Topic Modeling Via Contextual And Graph Information Fusion, Jiyuan Liu, Jiaxing Yan, Chunjiang Zhu, Xingyu Liu, Qing Li, Yanghui Rao
Neural Topic Modeling Via Contextual And Graph Information Fusion, Jiyuan Liu, Jiaxing Yan, Chunjiang Zhu, Xingyu Liu, Qing Li, Yanghui Rao
Computer Science Faculty Publications
Topic modeling is a powerful unsupervised tool for knowledge discovery. However, existing work struggles with generating limited-quality topics that are uninformative and incoherent, which hindering interpretable insights from managing textual data. In this paper, we improve the original variational autoencoder framework by incorporating contextual and graph information to address the above issues. First, the encoder utilizes topic fusion techniques to combine contextual and bag-of-words information well, and meanwhile exploits the constraints of topic alignment and topic sharpening to generate informative topics. Second, we develop a simple word co-occurrence graph information fusion strategy that efficiently increases topic coherence. On three benchmark …
Understanding Pii Leakage In Large Language Models: A Systematic Survey, Shuai Cheng, Zhao Li, Shu Meng, Mengxia Ren, Haitao Xu, Shuai Hao, Chuan Yue, Fang Zhang
Understanding Pii Leakage In Large Language Models: A Systematic Survey, Shuai Cheng, Zhao Li, Shu Meng, Mengxia Ren, Haitao Xu, Shuai Hao, Chuan Yue, Fang Zhang
Computer Science Faculty Publications
Large Language Models (LLMs) have demonstrated exceptional success across a variety of tasks, particularly in natural language processing, leading to their growing integration into numerous facets of daily life. However, this widespread deployment has raised substantial privacy concerns, especially regarding personally identifiable information (PII), which can be directly associated with specific individuals. The leakage of such information presents significant real-world privacy threats. In this paper, we conduct a systematic investigation into existing research on PII leakage in LLMs, encompassing commonly utilized PII datasets, evaluation metrics, and current studies on both PII leakage attacks and defensive strategies. Finally, we identify unresolved …
Energy-Based Deep Incomplete Multi-View Clustering, Ziyu Wang, Yiming Du, Rui Ning, Lusi Li
Energy-Based Deep Incomplete Multi-View Clustering, Ziyu Wang, Yiming Du, Rui Ning, Lusi Li
Computer Science Faculty Publications
Incomplete multi-view clustering (IMVC) deals with real-world scenarios where certain views are partially missing, posing significant challenges to effective clustering. Most existing IMVC approaches face a trade-off: imputation-free methods suffer from information bias and imbalance, while full-imputation methods risk introducing and propagating noise. To overcome these limitations, we propose Energy-Based Deep Incomplete Multi-View Clustering (Energy-DIMC), a novel selective-imputation framework that leverages energy-based models (EBMs) to guide reliable imputations and robust clustering. EBMs assess data compatibility by assigning lower energy to more coherent structures, effectively modeling complex inter-view and inter-sample dependencies. Inspired by EBMs, Energy-DIMC integrates four key components: 1) a …
Humans Vs. Llms On Open Domain Scientific Claim Verification: A Baseline Study, Benjamin Curtis, Stefania Dzhaman, Matthew Maisonave, Jian Wu
Humans Vs. Llms On Open Domain Scientific Claim Verification: A Baseline Study, Benjamin Curtis, Stefania Dzhaman, Matthew Maisonave, Jian Wu
Computer Science Faculty Publications
Verifying scientific claims is challenging for the general public because most people lack domain knowledge. Manual verification by subject domain experts is accurate, but it is obviously not scalable to meet the rising number of scientific claims on the Web. Whether the emerging large language models and large reasoning models can be used for scientific claim verification, and how their performances compare to humans, are still research questions. To this end, we developed a new benchmark MSVEC2 that consists of 138 claims from credible fact verification websites and science news outlets. Two tasks were given to both human and LLM …
Privshap: A Finer-Granularity Network Linearization Method For Private Inference, Xiangrui Xu, Zhenzhen Wang, Rui Ning, Chunsheng Xiu, Hongyi Wu
Privshap: A Finer-Granularity Network Linearization Method For Private Inference, Xiangrui Xu, Zhenzhen Wang, Rui Ning, Chunsheng Xiu, Hongyi Wu
Computer Science Faculty Publications
Private inference applies cryptographic techniques like homomorphic encryption, garble circuit and secret sharing to keep both sides privacy in a client-server setting during inference. It is often hindered by the high communication overheads, especially at non-linear activation layers such as ReLU. Hence ReLU pruning has been widely recognized as an efficient way to accelerate private inference. Existing approaches to ReLU pruning typically rely on coarse hypothesis, which assume an inverse correlation between the importance of ReLU and linear layers or shallow activation layers have less importance for universal models, to assign the budgets according to the layer while preserving the …